3 papers
cs.LG2025
LikeBench: Evaluating Subjective Likability in LLMs for Personalization
Md Awsafur Rahman, Adam Gabrys, Doug Kang +3
A personalized LLM should remember user facts, apply them correctly, and adapt over time to provide responses that the user prefers. Existing LLM personalization benchmarks are lar…
eess.AS2025
Investigating self-supervised features for expressive, multilingual voice conversion
Ãlvaro MartÃn-Cortinas, Daniel Sáez-Trigueros, Grzegorz Beringer +7
Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between d…
cs.SD2025
Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications
Biel Tura Vecino, Adam GabryÅ, Daniel MÄ twicki +4
Recent works have shown that modelling raw waveform directly from text in an end-to-end (E2E) fashion produces more natural-sounding speech than traditional neural text-to-speech (…